© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1052
    Prev
    Next
    INDEX
    Explanations

    sexual assault and domestic violence resources

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects names of formal institutions and organizations (e.g., agencies, institutes, centers, or professional bodies).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extruder
    0.62
    department
    0.61
     pero
    0.60
    untamiento
    0.60
    🐮
    0.60
     konto
    0.59
     saddo
    0.59
    🚜
    0.58
    👛
    0.58
     poté
    0.57
    POSITIVE LOGITS
     Studies
    0.68
     Education
    0.61
     Medicine
    0.61
     Sciences
    0.61
     Aeronautics
    0.60
     Affairs
    0.56
     Research
    0.55
     therapeutics
    0.55
     Needs
    0.54
     Environments
    0.54
    Activations Density 0.279%

    No Known Activations